1. Enhancing the quality of milk prediction using random forest algorithm and logistic regression algorithm.
- Author
-
Vishnu, K. and Kumar, S. Prem
- Subjects
RANDOM forest algorithms ,SCIENTIFIC literature ,TECHNICAL literature ,TECHNICAL reports ,SAMPLE size (Statistics) ,MILK quality - Abstract
Changes to the milk's quality profile brought about by the introduction of various pollutants. There have been reports in the scientific literature of technological devices that use portable sensors to investigate both direct and indirect transduction events. In order to identify milk impurities, conductive sensors that are equipped with selective sensitivity films are utilised the majority of the time. On the other hand, it is essential to keep in mind that these sensors need to be calibrated and that they exhibit drift as they get older. It is of the utmost importance to own a detecting system that is not only inexpensive but also sensitive, quick, and simple to operate. Methodologies and Instruments for Research: For the purpose of collecting the twenty samples, two groups of 10 were utilised. The random forest algorithm is utilised in Group 1, one of the groups. The approach of logistic regression is utilised for Group 2 in this study. It is estimated that the G power test is successful approximately 80 percent of the time. G power equals 0.80, and β equals 0.05. These are the parameters that make up the power arrangement. Using a sample size of n = 20, the categorization is carried out by employing two different kinds of algorithms in conjunction with the scaling provided by the Python Extension. With a p-value of less than 0.05 and an independent sample t-test of 0.0467, the results demonstrate that the Random Forest Algorithm works better than the logistic regression algorithm. The Random Forest Algorithm achieves an accuracy of 94.39 percent, while the logistic regression algorithm achieves an accuracy of 81 percent. Taking into consideration the findings, it would appear that the Random forest method is superior than the logistic regression approach in terms of accuracy (99.86 percent) when it comes to predicting milk quality. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF